In radiomics studies, researchers usually need to develop a supervised machine learning model to map image features onto the clinical conclusion. A classical machine learning pipeline consists of several steps, including normalization, feature selection, and classification. It is often tedious to find an optimal pipeline with appropriate combinations. We designed an open-source software package named FeAture Explorer (FAE). It was programmed with Python and used NumPy, pandas, and scikit-learning modules. FAE can be used to extract image features, preprocess the feature matrix, develop different models automatically, and evaluate them with common clinical statistics. FAE features a user-friendly graphical user interface that can be used by radiologists and researchers to build many different pipelines, and to compare their results visually. To prove the effectiveness of FAE, we developed a candidate model to classify the clinical-significant prostate cancer (CS PCa) and non-CS PCa using the PROSTATEx dataset. We used FAE to try out different combinations of feature selectors and classifiers, compare the area under the receiver operating characteristic curve of different models on the validation dataset, and evaluate the model using independent test data. The final model with the analysis of variance as the feature selector and linear discriminate analysis as the classifier was selected and evaluated conveniently by FAE. The area under the receiver operating characteristic curve on the training, validation, and test dataset achieved results of 0.838, 0.814, and 0.824, respectively. FAE allows researchers to build radiomics models and evaluate them using an independent testing dataset. It also provides easy model comparison and result visualization. We believe FAE can be a convenient tool for radiomics studies and other medical studies involving supervised machine learning.

Background: Accurate lymph node metastasis (LNM) prediction in colorectal cancer (CRC) patients is of great significance for treatment decision making and prognostic evaluation. We aimed to develop and validate a clinical-radiomics nomogram for the individual preoperative prediction of LNM in CRC patients. Methods: We enrolled 766 patients (458 in the training set and 308 in the validation set) with clinicopathologically confirmed CRC. We included nine significant clinical risk factors (age, sex, preoperative carbohydrate antigen 19-9 (CA19-9) level, preoperative carcinoembryonic antigen (CEA) level, tumor size, tumor location, histotype, differentiation and M stage) to build the clinical model. We used analysis of variance (ANOVA), relief and recursive feature elimination (RFE) for feature selection (including clinical risk factors and the imaging features of primary lesions and peripheral lymph nodes), established classification models with logistic regression analysis and selected the respective candidate models by fivefold cross-validation. Then, we combined the clinical risk factors, primary lesion radiomics features and peripheral lymph node radiomics features of the candidate models to establish combined predictive models. Model performance was assessed by the area under the receiver operating characteristic (ROC) curve (AUC). Finally, decision curve analysis (DCA) and a nomogram were used to evaluate the clinical usefulness of the model. Results: The clinical-primary lesion radiomics-peripheral lymph node radiomics model, with the highest AUC value (0.7606), was regarded as the candidate model and had good discrimination and calibration in both the training and validation sets. DCA demonstrated that the clinical-radiomics nomogram was useful for preoperative prediction in the clinical environment. Conclusion: The present study proposed a clinical-radiomics nomogram with a combination of clinical risk factors and radiomics features that can potentially be applied in the individualized preoperative prediction of LNM in CRC patients.